Scientific and Technological Text Knowledge Extraction Method of based on Word Mixing and GRU

TL;DR

This paper introduces a novel end-to-end neural network approach combining word mixing, GRU, and self-attention mechanisms to improve the extraction of entity-relation triples from Chinese scientific texts.

Contribution

It proposes a new knowledge extraction method that enhances relationship extraction accuracy using word mixture vectors and self-attention in a joint extraction framework.

Findings

Improved extraction accuracy for scientific and technological texts.

Effective handling of Chinese scientific language complexities.

Enhanced preservation of entity-relationship associations.

Abstract

The knowledge extraction task is to extract triple relations (head entity-relation-tail entity) from unstructured text data. The existing knowledge extraction methods are divided into "pipeline" method and joint extraction method. The "pipeline" method is to separate named entity recognition and entity relationship extraction and use their own modules to extract them. Although this method has better flexibility, the training speed is slow. The learning model of joint extraction is an end-to-end model implemented by neural network to realize entity recognition and relationship extraction at the same time, which can well preserve the association between entities and relationships, and convert the joint extraction of entities and relationships into a sequence annotation problem. In this paper, we propose a knowledge extraction method for scientific and technological resources based on word mixture and GRU, combined with word mixture vector mapping method and self-attention mechanism, to effectively improve the effect of text relationship extraction for Chinese scientific and technological resources.